SANA-1.5 4.8B (+ Inference Scaling)
Reported on 4 benchmarks across 4 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Audio2 results
- Overall· 2025-01-300.8best: 0.95 (SD3.5-Medium+Flow-GRPO)
- Overall· 2025-01-300.8best: 0.95 (SD3.5-Medium+Flow-GRPO)
Medical1 result
- Overall· 2025-01-300.8best: 0.95 (SD3.5-Medium+Flow-GRPO)
Natural Language Processing1 result
- Overall· 2025-01-300.8best: 0.95 (SD3.5-Medium+Flow-GRPO)